Abstract
Globally, the rate of preterm births is increasing and this is resulting in significant health, development and economic problems. Current methods for the early detection of such births are inadequate. However, there has been some evidence to suggest that the analysis of uterine electrical signals, collected from the abdominal surface, could provide an independent and easier way to diagnose true labour and detect when preterm delivery is about to occur. Using advanced machine learning algorithms, in conjunction with electrohysterography signal processing, numerous studies have focused on detecting true labour several days prior to the event. In this paper however, the electrohysterography signals have been used to detect preterm births. This has been achieved using an open dataset that contains 262 records for women who delivered at term and 38 who delivered prematurely. Several new features from Electromyography studies have been utilized, as well as feature-ranking techniques to determine their discriminative capabilities in detecting term and preterm records. Seven artificial neural network algorithms are considered with the results showing that the Radial Basis Function Neural Network classifier performs the best, with 85% sensitivity, 80% specificity, 90% area under the curve and a 17% mean error rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
37steps, Pattern Recognition Tools. Version 5 (2013)
Alamedine, D., Khalil, M.: Marque.: Comparison of different EHG feature selection methods for the detection of preterm labor. Computational and Mathematical Methods in Medicine 10(6), 24–26 (2013)
Bulletin, S.: Statistical Bulletin Gestation-specific Infant Mortality inEngland and Wales. National Office for Statistics (2011)
Fergus, P., Cheung, P., Hussain, A., Al-Jumeily, D., Dobbins, C., Iram, S.: Prediction of Preterm Deliveries from EHG Signals Using Machine Learning. PloS One 8(10), 130–135 (2011)
Hassan, M., Muszynski, C., Alexandersson, A., Marque, C.: Nonlinear Correlation Analysis of External Uterine Electromyography. IEEE Transactions on BioMedical Engineering 60(4), 1160–1166 (2013)
Lange, L., Vaeggemose, A., Kidmose, P., Mikkelsen, E., Uldbjerg, N., Johansen, P.: Velocity and directionality of the electrohysterographic signal propagation. PloS One 9(1), 199–205 (2014)
Leman, H., Marque, C., Gondry, J.: Use of the electrohyster- ogram signal for characterization of contractions during pregnancy. IEEE Trans. Biomed. Eng. 46(10), 1222–1229 (1999)
Lucovnik, M., Maner, W.L., Chambliss, L.R., Blumrick, R., Balducci, J., Novak-Antolic, Z., Garfield, R.E.: Noninvasive uterine electromyography for prediction of preterm delivery. American Journal of Obstetrics and Gynecology 204(3), 156–162 (2011)
Maner, W.: Predicting term and preterm delivery with transabdominal uterine electromy-ography. Obstetrics & Gynecology 101(6), 1254–1260 (2003)
PhysioNet. The Term -Preterm EHG Database (TPEHG- DB). physionet.org (2012)
Richman, J., Moorman, J.: Physiological time-series analysis using approximate entropy and sample entropy. American Journal of Physiology 49, H2039–H2049 (2000)
Vasak, B., Graatsma, E.M., Hekman-Drost, E., Eijkemans, M.J., van Leeuwen, J.H.S., Visser, G.H., Jacod, B.C.: Uterine electromyography for identification of first-stage labor arrest in term nulliparous women with spontaneous onset of labor. American Journal of Obstetrics and Gynecology 209(3), 232.e1–232.e8 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Fergus, P., Idowu, I.O., Hussain, A.J., Dobbins, C., Al-Askar, H. (2014). Evaluation of Advanced Artificial Neural Network Classification and Feature Extraction Techniques for Detecting Preterm Births Using EHG Records. In: Huang, DS., Han, K., Gromiha, M. (eds) Intelligent Computing in Bioinformatics. ICIC 2014. Lecture Notes in Computer Science(), vol 8590. Springer, Cham. https://doi.org/10.1007/978-3-319-09330-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-09330-7_37
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09329-1
Online ISBN: 978-3-319-09330-7
eBook Packages: Computer ScienceComputer Science (R0)